article · Sensors
Demand for high-quality date palm fruit is rising, but conventional sorting and grading methods rely heavily on intensive manual labour and mechanical handling that can damage the fruit and diminish its value. To address this, an automated, non-contact classification model called DateNET was developed using a convolutional neural network. The model assesses date varieties through digital image analysis based on colour differences and geometric parameters. DateNET incorporates a fixed architecture structured with five alternating layers of two-dimensional convolutions, maximum pooling, and dropout operations. When evaluated on fruit colour alone, the model achieved a validation accuracy of 85.24 per cent, while classification using only geometric parameters reached 87.62 per cent. Combining both colour and geometry significantly improved performance, resulting in an overall classification accuracy of 93.41 per cent.
Sorting date palm fruits mechanically or manually is labour-intensive and can cause physical damage, reducing product quality and economic value. Non-contact image analysis powered by neural networks offers an automated alternative that protects the fruit. By accurately identifying varieties without physical contact, such systems support more reliable quality control and post-harvest handling in agricultural supply chains.
This technology offers an automated sorting solution for date processors, packing facilities, and agricultural quality inspectors seeking to minimise fruit damage during grading. The research demonstrates an applied and validated model tested on image data, achieving over 93 per cent accuracy when combining colour and geometric features. Practical deployment would require integration into digital sorting machinery or conveyor vision systems in real-world packing environments.
AI-generated from the published abstract. Always read the original work before citing.
The popularity and demand for high-quality date palm fruits (<i>Phoenix dactylifera</i> L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/s24020558
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
